Research map / Image generation / Editing and style transfer
Bridging the Visual Gap: Wide-Range Image Blending
Chia-Ni Lu, Ya-Chu Chang, Wei-Chen Chiu
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add contextual attention (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 35.86 -> 36.13 | No clear effect |
| add contextual attention (ablation) | Wide-range image blending model · Wide-range image blending ablation | KID mean: 0.0105 -> 0.0116 | No clear effect |
| add pixel reconstruction loss (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 42.14 -> 36.13 | Improved |
| add feature reconstruction loss (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 37.21 -> 36.13 | Improved |
| add texture consistency loss (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 44.74 -> 36.13 | Improved |
| add feature consistency loss (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 45.29 -> 36.13 | Improved |
| add adversarial losses (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 57.62 -> 36.13 | Improved |
| include the fine-tuning stage after self-reconstruction training (ablation) | Wide-range image blending model · Wide-range image blending ablation | FID: 46.30 -> 36.13 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StructureFlow — StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (ICCV 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Generative Image Inpainting With Contextual Attention (CVPR 2018 · similarity 0.87)
- Contextual-based Image Inpainting: Infer, Match, and Translate (ECCV 2018 · similarity 0.87)
- High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis (CVPR 2017 · similarity 0.87)
- Learning to Blend Photos (ECCV 2018 · similarity 0.87)
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (ICLR 2021 · similarity 0.86)
- Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
